© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1174
    Prev
    Next
    INDEX
    Explanations

    specific geographic locations and legal references within a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    U.S. states

    np_acts-logits-general · gemini-2.0-flash

    US states after prepositions/punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mondial
    -0.77
     EUROPEAN
    -0.74
    european
    -0.73
     Europeans
    -0.72
     EUROPE
    -0.70
    Europe
    -0.70
    europe
    -0.70
    ISPR
    -0.69
    European
    -0.68
     europeo
    -0.67
    POSITIVE LOGITS
     Pennsylvania
    1.48
     Illinois
    1.46
     Texas
    1.43
     Florida
    1.38
     Ohio
    1.37
     Arizona
    1.34
     California
    1.31
     Tennessee
    1.31
     Wisconsin
    1.30
     Maryland
    1.30
    Activations Density 0.692%

    No Known Activations